Methods and systems for determining stopping point
A computer-implemented method for identifying a stopping point of an active learning process includes calculating an error rate for a set of documents, determining whether minimum coding exists, checking an error rate, detecting that an uncertainty rate decreases, and displaying an indication that the stopping point has been reached. A computing system for determining a stopping point of an active learning process includes a processors and a memory storing instructions that, when executed, cause the computing system to calculate an error rate, determine that minimum coding exists, check an error rate, detect decreasing uncertainty rate, and display a stopping point indication. A non-transitory computer readable medium storing program instructions that when executed, cause a computer system to calculate an error rate, determine that minimum coding exists, check an error rate, detect decreasing uncertainty rate, and display a stopping point indication.
1. A computer-implemented method for identifying a stopping point of an active learning process, comprising:
calculating a first estimated error rate and a second estimated error rate in a sampling window of the active learning process,
calculating a first uncertain rank count and a second uncertain rank count in the sampling window of the active learning process,
when the first estimated error rate and the second estimated error rate in the sampling window of the active learning process do not, respectively, exceed a target error rate, and
when the second uncertain rank count does not exceed the first uncertain rank count,
displaying, in a display of a computing device, an indication that the stopping point has been reached.
2. The computer-implemented method of claim 1 , wherein calculating the first estimated error rate includes receiving a coverage review indication from a user.
3. The computer-implemented method of claim 1 , wherein calculating the first estimated error rate includes determining whether the user has coded a minimum number of documents.
4. The computer-implemented method of claim 1 , wherein calculating the first estimated error rate includes determining whether the user has coded a minimum number of document groups.
5. The computer-implemented method of claim 1 , wherein the target error rate is a configurable constant.
6. The computer-implemented method of claim 1 , wherein calculating the first uncertain rank count and the second uncertain rank count in the sampling window of the active learning process includes comparing uncertain rank counts across a configurable number of previous builds.
7. The computer-implemented method of claim 1 , wherein displaying, in the display device of the computing device, the indication that the stopping point has been reached includes
generating a message indicating that the stopping point has been reached, and
transmitting the message via one or both of (i) a push message, and (ii) an email message.
8. A computing system for determining a stopping point of an active learning process, comprising
one or more processors; and
a memory storing instructions that, when executed, cause the computing system to:
calculate a first estimated error rate and a second estimated error rate in a sampling window of the active learning process,
calculate a first uncertain rank count and a second uncertain rank count in the sampling window of the active learning process,
when the first estimated error rate and the second estimated error rate in the sampling window of the active learning process do not, respectively, exceed a target error rate, and
when the second uncertain rank count does not exceed the first uncertain rank count,
display, in a display of a computing device, an indication that the stopping point has been reached.
9. The computing system of claim 8 , the memory including further instructions that when executed, cause the computing system to:
receive a coverage review indication from a user.
10. The computing system of claim 8 , the memory including further instructions that when executed, cause the computing system to:
determine whether the user has coded a minimum number of documents.
11. The computing system of claim 8 , the memory including further instructions that when executed, cause the computing system to:
determine whether the user has coded a minimum number of document groups.
12. The computing system of claim 8 , wherein the target error rate is a configurable constant.
13. The computing system of claim 8 , the memory including further instructions that when executed, cause the computing system to:
compare uncertain rank counts across a configurable number of previous builds.
14. The computing system of claim 8 , the memory including further instructions that when executed, cause the computing system to:
generate a message indicating that the stopping point has been reached, and
transmit the message via one or both of (i) a push message, and (ii) an email message.
15. A non-transitory computer readable medium storing program instructions that when executed, cause a computer system to:
calculate a first estimated error rate and a second estimated error rate in a sampling window of the active learning process,
calculate a first uncertain rank count and a second uncertain rank count in the sampling window of the active learning process,
when the first estimated error rate and the second estimated error rate in the sampling window of the active learning process do not, respectively, exceed a target error rate, and
when the second uncertain rank count does not exceed the first uncertain rank count,
display, in a display of a computing device, an indication that the stopping point has been reached.
16. The non-transitory computer readable medium of claim 15 , including further program instructions that when executed, cause a computer system to:
receive a coverage review indication from a user.
17. The non-transitory computer readable medium of claim 15 , including further program instructions that when executed, cause a computer system to:
determine whether the user has coded a minimum number of documents.
18. The non-transitory computer readable medium of claim 15 , wherein the target error rate is a configurable constant.
19. The non-transitory computer readable medium of claim 15 , including further program instructions that when executed, cause a computer system to:
compare uncertain rank counts across a configurable number of previous builds.
20. The non-transitory computer readable medium of claim 15 , including further program instructions that when executed, cause a computer system to:
generate a message indicating that the stopping point has been reached, and
transmit the message via one or both of (i) a push message, and (ii) an email message.